Predict Circle instead of line

[SabareeshGC]

Just finished chapter 1 homework and i challenged myself to predict a circle instead of line but i am out of luck.

Here is the equation. x2+y2=r2

I created dataset using static R=2 and produced y for given x value. x rages from -1 to 1 steps of 0.1

interestingly now we have 2 outputs instead of 1 because circles -y and y

Here is one architecture but no luck

class LinearLine(nn.Module):
    def __init__(self, input_dim=1, hidden_dim=10, output_dim=2):
        super(LinearLine, self).__init__()
        self.layer_1 = nn.Linear(input_dim, hidden_dim)
        nn.init.kaiming_uniform_(self.layer_1.weight, nonlinearity="relu")
        self.layer2 = nn.Linear(hidden_dim, hidden_dim)
        self.layer_3 = nn.Linear(hidden_dim, output_dim)
       
    def forward(self, x):
        x = torch.nn.functional.gelu(self.layer_1(x))
        x = torch.nn.functional.gelu(self.layer2(x))
        x = torch.nn.functional.sigmoid(self.layer_3(x))

        return x